mlsanityData to 14 Oct 2026

Robust and Efficient Communication in Multi-Agent Reinforcement Learning

arXiv 2511.11393 ↗First posted 14 Nov 2025cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Multi-agent reinforcement learning (MARL) has made significant strides in enabling coordinated behaviors among autonomous agents. However, most existing approaches assume that communication is instantaneous, reliable, and has unlimited bandwidth; these conditions are rarely met in real-world deployments. This survey systematically reviews recent advances in robust and efficient communication strategies for MARL under realistic constraints, including message perturbations, transmission delays, and limited bandwidth. Furthermore, because the challenges of low-latency reliability, bandwidth-intensive data sharing, and communication-privacy trade-offs are central to practical MARL systems, we focus on three applications involving cooperative autonomous driving, distributed simultaneous localization and mapping, and federated learning. Finally, we identify key open challenges and future research directions, advocating a unified approach that co-designs communication, learning, and robustness to bridge the gap between theoretical MARL models and practical implementations.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 19 of its 48 references that are in the map. First posted on arXiv 14 Nov 2025.

Builds on

19 of 48 references.

References · 19

  1. 2021FedKD: Communication Efficient Federated Learning via Knowledge Distillationcited by 187
  2. 2023Large AI Model-Based Semantic Communicationscited by 35
  3. 2020Learning Structured Communication for Multi-agent Reinforcement Learningcited by 21
  4. 2023Multi-Agent Reinforcement Learning for Connected and Automated Vehicles Control: Recent Advancements and Future Prospectscited by 18
  5. 2022RoMFAC: A robust mean-field actor-critic reinforcement learning against adversarial perturbations on statescited by 16
  6. 2025Multi-Agent Reinforcement Learning for Resources Allocation Optimization: A Surveycited by 14
  7. 2022Goal-Oriented Semantic Communications for 6G Networkscited by 8
  8. 2023Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generationcited by 6
  9. 2023Heterogeneous Embodied Multi-Agent Collaborationcited by 6
  10. 2023Robust Multi-Agent Reinforcement Learning by Mutual Information Regularizationcited by 6
  11. 2024Effective Communication with Dynamic Feature Compressioncited by 6
  12. 2021The Gradient Convergence Bound of Federated Multi-Agent Reinforcement Learning with Efficient Communicationcited by 5
7 more
  1. 2021Multi-Agent Deep Reinforcement Learning For Persistent Monitoring With Sensing, Communication, and Localization Constraintscited by 4
  2. 2022Distributed Deep Reinforcement Learning: A Survey and A Multi-Player Multi-Agent Learning Toolboxcited by 4
  3. 2023Robust Multi-agent Communication via Multi-view Message Certificationcited by 3
  4. 2024Evolutionary Multi-agent Reinforcement Learning in Group Social Dilemmascited by 3
  5. 2025DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Modelscited by 3
  6. 2023Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learningcited by 2
  7. 2025Denoising and Reconstruction of Nonlinear Dynamics using Truncated Reservoir Computingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026AgentComm-Bench: Stress-Testing Cooperative Embodied AI Under Latency, Packet Loss, and Bandwidth Collapsecited by 1
  2. 2026Wireless Communication Enhanced Value Decomposition for Multi-Agent Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints
  2. 2026Robust and Efficient Communication for Multi-Agent Learning
  3. 2026Communication Methods in Multi-Agent Reinforcement Learning
  4. 2024Fully Independent Communication in Multi-Agent Reinforcement Learning
  5. 2026The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMs
  6. 2025Reward-Independent Messaging for Decentralized Multi-Agent Reinforcement Learning
  7. 2025Goal-Oriented Multi-Agent Reinforcement Learning for Decentralized Agent Teams
  8. 2023Context-aware Communication for Multi-agent Reinforcement Learning